REGION-BASED SHAPE-MATCHING FOR AUTOMATIC IMAGE ANNOTATION AND QUERY-BY-EXAMPLE

We present a method for automatic image annotation and retrieval based on query-by-example by region-based shape matching. The proposed meth od consists of two parts: region selection and shape matching. In the first part, the image is partitioned into disjoint, connected regions with more-or-less uniform color, whose boundaries coincide with spatia l edge locations. Each region or valid combinations of neighboring reg ions constitute ''potential objects.'' In the second part, the shape o f each potential object is tested to determine whether it matches one from a set of given templates. To this effect, we propose a new shape matching method, which is translation-, rotation-, and isotropic scale -invariant, where the boundary of each potential object, as well as of each template, is represented by a B-spline. We, then, identify corre spondences between the joint points of the B-splines of potential obje cts and templates by using a modal matching method. These corresponden ces are used to estimate the parameters of an affine mapping to regist er the object with the template. A proximity measure is then computed between the two contours based on the Hausdorff distance. We demonstra te the performance of the proposed method on a variety of images. (C) 1997 Academic Press.